from pathlib import Path
import math
import re

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import display

sns.set_theme(style="whitegrid", context="talk")
pd.set_option("display.max_columns", 200)
pd.set_option("display.width", 220)

DATA_DIR = Path("data")
if not DATA_DIR.exists():
    raise FileNotFoundError("Expected directory 'data/' with split CSV files.")

print(f"Using data directory: {DATA_DIR.resolve()}")
print(f"pandas={pd.__version__}, seaborn={sns.__version__}")

Using data directory: /home/dig/repositories/roseau-full-bench/results/use_case/walk/data
pandas=2.3.3, seaborn=0.13.2

BOOL_COLS_COMMITS = ["is_merge_commit", "has_java_changes", "has_pom_changes"]
BOOL_COLS_BCS = ["is_excluded_symbol", "is_deprecated_removal", "is_internal_removal"]
NUMERIC_COLS_COMMITS = [
    "days_since_prev_commit", "files_changed", "loc_added", "loc_deleted",
    "all_api_types_count", "all_api_methods_count", "all_api_fields_count", "all_api_symbols_count",
    "exported_types_count", "exported_methods_count", "exported_fields_count",
    "deprecated_count", "internal_count",
    "breaking_changes_count", "binary_breaking_changes_count", "source_breaking_changes_count",
    "checkout_time_ms", "classpath_time_ms", "api_time_ms", "diff_time_ms", "stats_time_ms",
]


def parse_bool_series(s: pd.Series) -> pd.Series:
    vals = s.astype(str).str.lower().map({"true": True, "false": False})
    return vals.eq(True)


def load_split_data(data_dir: Path):
    commits_frames = []
    bcs_frames = []

    commit_files = sorted(data_dir.glob("*-commits.csv"))
    bc_files = sorted(data_dir.glob("*-bcs.csv"))

    libs_from_commits = {p.name.replace("-commits.csv", "") for p in commit_files}
    libs_from_bcs = {p.name.replace("-bcs.csv", "") for p in bc_files}

    missing_pairs = sorted(libs_from_commits.symmetric_difference(libs_from_bcs))
    if missing_pairs:
        print("Warning: some libraries do not have both files:", missing_pairs)

    for path in commit_files:
        lib = path.name.replace("-commits.csv", "")
        df = pd.read_csv(path)
        if "library" not in df.columns:
            df["library"] = lib

        df["date_utc"] = pd.to_datetime(df["date_utc"], errors="coerce", utc=True)
        df = df.dropna(subset=["date_utc"]).sort_values("date_utc").reset_index(drop=True)

        for c in NUMERIC_COLS_COMMITS:
            if c in df.columns:
                df[c] = pd.to_numeric(df[c], errors="coerce").fillna(0)

        for c in BOOL_COLS_COMMITS:
            if c in df.columns:
                df[c] = parse_bool_series(df[c])

        # Derived commit-level features
        df["net_loc"] = df["loc_added"] - df["loc_deleted"]
        df["abs_loc_churn"] = df["loc_added"] + df["loc_deleted"]
        df["exported_symbols_count"] = (
            df["exported_types_count"] + df["exported_methods_count"] + df["exported_fields_count"]
        )
        df["all_symbols_count"] = (
            df["all_api_types_count"] + df["all_api_methods_count"] + df["all_api_fields_count"]
        )
        df["breaks_per_1k_exported"] = (
            df["breaking_changes_count"] / df["exported_symbols_count"].replace(0, np.nan) * 1000
        ).replace([np.inf, -np.inf], np.nan).fillna(0)
        df["internal_share"] = (
            df["internal_count"] / df["all_symbols_count"].replace(0, np.nan)
        ).replace([np.inf, -np.inf], np.nan).fillna(0)
        df["deprecated_share"] = (
            df["deprecated_count"] / df["exported_symbols_count"].replace(0, np.nan)
        ).replace([np.inf, -np.inf], np.nan).fillna(0)

        commits_frames.append(df)

    for path in bc_files:
        lib = path.name.replace("-bcs.csv", "")
        df = pd.read_csv(path)
        if "library" not in df.columns:
            df["library"] = lib

        for c in BOOL_COLS_BCS:
            if c in df.columns:
                df[c] = parse_bool_series(df[c])

        bcs_frames.append(df)

    commits = pd.concat(commits_frames, ignore_index=True) if commits_frames else pd.DataFrame()
    bcs = pd.concat(bcs_frames, ignore_index=True) if bcs_frames else pd.DataFrame()

    return commits, bcs, sorted(libs_from_commits.intersection(libs_from_bcs)), missing_pairs


commits_df, bcs_df, libraries, missing_pairs = load_split_data(DATA_DIR)

print(f"Libraries with complete pairs: {len(libraries)}")
print(f"Commit rows: {len(commits_df):,}")
print(f"Breaking-change rows: {len(bcs_df):,}")
if missing_pairs:
    print("Libraries missing one side:", missing_pairs)

Libraries with complete pairs: 35
Commit rows: 146,334
Breaking-change rows: 658,235

coverage = commits_df.groupby("library").agg(
    commits=("commit_sha", "count"),
    first_commit=("date_utc", "min"),
    last_commit=("date_utc", "max"),
    commits_with_breaks=("breaking_changes_count", lambda s: int((s > 0).sum())),
    total_reported_breaks=("breaking_changes_count", "sum"),
    final_exported_symbols=("exported_symbols_count", "last"),
    final_internal_symbols=("internal_count", "last"),
    merge_commit_rate=("is_merge_commit", "mean"),
    java_change_rate=("has_java_changes", "mean"),
).sort_values("total_reported_breaks", ascending=False)

# Cross-check: commit-level break count vs row-level BC records
bc_counts_from_rows = bcs_df.groupby("library").size().rename("bc_rows")
coverage = coverage.join(bc_counts_from_rows, how="left").fillna({"bc_rows": 0})
coverage["bc_count_delta"] = coverage["total_reported_breaks"] - coverage["bc_rows"]

coverage.head(20)

fig, axes = plt.subplots(1, 2, figsize=(18, max(7, 0.45 * len(coverage))))

commits_plot = coverage.sort_values("commits", ascending=False).reset_index()
sns.barplot(data=commits_plot, y="library", x="commits", ax=axes[0], color="#2a9d8f")
axes[0].set_title("Libraries by Commit Count")
axes[0].set_xlabel("Commits analyzed")
axes[0].set_ylabel("")

# Use row-level BC counts for direct event volume comparison
bcs_plot = coverage.sort_values("bc_rows", ascending=False).reset_index()
sns.barplot(data=bcs_plot, y="library", x="bc_rows", ax=axes[1], color="#e76f51")
axes[1].set_title("Libraries by Breaking-Change Events")
axes[1].set_xlabel("Breaking-change records")
axes[1].set_ylabel("")

plt.tight_layout()
plt.show()

# Per-library timeline plot (API size + vertical BC bars per commit)
libs_order = coverage.sort_values("commits", ascending=False).index.tolist()

for lib in libs_order:
    d = commits_df[commits_df["library"] == lib].sort_values("date_utc").copy()
    if d.empty:
        continue

    fig, ax = plt.subplots(figsize=(14, 4.5))

    # API size evolution
    ax.plot(d["date_utc"], d["all_api_symbols_count"], color="#1d3557", linewidth=1.6, label="All API symbols")
    ax.plot(d["date_utc"], d["exported_symbols_count"], color="#2a9d8f", linewidth=1.6, label="Exported symbols")

    # Vertical red bars for commits with breaking changes
    bc_commits = d[d["breaking_changes_count"] > 0]
    if not bc_commits.empty:
        ymax = max(float(d["all_api_symbols_count"].max()), 1.0)
        # bar height scales with break count to preserve intensity signal
        bar_top = (bc_commits["breaking_changes_count"] / bc_commits["breaking_changes_count"].max()) * ymax
        ax.vlines(
            bc_commits["date_utc"],
            ymin=0,
            ymax=bar_top,
            color="red",
            alpha=0.45,
            linewidth=1.0,
            label="Breaking change commit" if len(bc_commits) else None,
        )

    ax.set_title(f"{lib}: API evolution and breaking-change introductions")
    ax.set_xlabel("Date")
    ax.set_ylabel("Symbol count")
    ax.grid(alpha=0.25)

    handles, labels = ax.get_legend_handles_labels()
    # deduplicate legend labels
    uniq = dict(zip(labels, handles))
    ax.legend(uniq.values(), uniq.keys(), loc="upper left")

    plt.tight_layout()
    plt.show()
    plt.close(fig)

# Libraries with largest final exported APIs
focus_libs = (
    coverage.sort_values("final_exported_symbols", ascending=False)
    .index
    .tolist()
)

fig, axes = plt.subplots(18, 2, figsize=(18, 100), sharex=False)
axes = axes.flatten()

for i, lib in enumerate(focus_libs):
    d = commits_df[commits_df["library"] == lib].copy().sort_values("date_utc")
    if d.empty:
        axes[i].axis("off")
        continue

    d["rolling_break_risk"] = d["breaks_per_1k_exported"].rolling(window=60, min_periods=10).mean()

    ax = axes[i]
    ax.plot(d["date_utc"], d["exported_symbols_count"], label="Exported symbols", color="#264653", linewidth=2)
    ax.plot(d["date_utc"], d["internal_count"], label="Internal symbols", color="#8ab17d", linewidth=1.6)
    ax.set_title(lib)
    ax.set_ylabel("Symbol count")
    ax.grid(alpha=0.25)

    ax2 = ax.twinx()
    ax2.plot(d["date_utc"], d["rolling_break_risk"], label="Rolling breaks/1k exported", color="#e76f51", linewidth=1.6)
    ax2.set_ylabel("Breaks per 1k")

    lines, labels = ax.get_legend_handles_labels()
    lines2, labels2 = ax2.get_legend_handles_labels()
    ax.legend(lines + lines2, labels + labels2, loc="upper left", fontsize=9)

for j in range(len(focus_libs), len(axes)):
    axes[j].axis("off")

plt.suptitle("API size evolution and normalized breaking-change risk", y=1.02)
plt.tight_layout()
plt.show()

sample = commits_df[["library", "abs_loc_churn", "files_changed", "breaking_changes_count", "breaks_per_1k_exported"]].copy()
if len(sample) > 100_000:
    sample = sample.sample(100_000, random_state=42)

fig, axes = plt.subplots(1, 2, figsize=(18, 7))

sns.scatterplot(
    data=sample,
    x="abs_loc_churn",
    y="breaking_changes_count",
    hue="library",
    alpha=0.25,
    linewidth=0,
    s=18,
    legend=False,
    ax=axes[0],
)
axes[0].set_xscale("symlog", linthresh=1)
axes[0].set_yscale("symlog", linthresh=1)
axes[0].set_title("Code churn vs breaking changes per commit")
axes[0].set_xlabel("LOC churn (added + deleted)")
axes[0].set_ylabel("Breaking changes")

sns.scatterplot(
    data=sample,
    x="files_changed",
    y="breaks_per_1k_exported",
    hue="library",
    alpha=0.25,
    linewidth=0,
    s=18,
    legend=False,
    ax=axes[1],
)
axes[1].set_xscale("symlog", linthresh=1)
axes[1].set_yscale("symlog", linthresh=0.1)
axes[1].set_title("Files changed vs normalized break risk")
axes[1].set_xlabel("Files changed")
axes[1].set_ylabel("Breaks per 1k exported symbols")

plt.tight_layout()
plt.show()

# Top kind distribution by library
kind_counts = (
    bcs_df.groupby(["library", "kind"]).size().rename("count").reset_index()
)

top_kinds = bcs_df["kind"].value_counts().head(15).index
kind_matrix = (
    kind_counts[kind_counts["kind"].isin(top_kinds)]
    .pivot(index="library", columns="kind", values="count")
    .fillna(0)
)
kind_matrix = kind_matrix.loc[kind_matrix.sum(axis=1).sort_values(ascending=False).index]

plt.figure(figsize=(18, 20))
sns.heatmap(np.log1p(kind_matrix), cmap="YlOrRd", cbar_kws={"label": "log(1 + BC events)"})
plt.title("Breaking-change kind intensity by library (top 15 kinds)")
plt.xlabel("Breaking-change kind")
plt.ylabel("Library")
plt.tight_layout()
plt.show()

compat = (
    bcs_df.groupby(["library", "compatibility"]).size().rename("count").reset_index()
)
compat["share"] = compat.groupby("library")["count"].transform(lambda s: s / s.sum())

top_libs_for_compat = coverage.sort_values("bc_rows", ascending=False).head(12).index
plot_compat = compat[compat["library"].isin(top_libs_for_compat)]

plt.figure(figsize=(18, 8))
sns.barplot(data=plot_compat, x="library", y="share", hue="compatibility")
plt.title("Compatibility profile by library (top 12 by BC count)")
plt.xlabel("Library")
plt.ylabel("Share of breaking changes")
plt.xticks(rotation=70, ha="right")
plt.tight_layout()
plt.show()

flags = (
    bcs_df.groupby("library").agg(
        total_bcs=("kind", "count"),
        excluded_bcs=("is_excluded_symbol", "sum"),
        internal_removals=("is_internal_removal", "sum"),
        deprecated_removals=("is_deprecated_removal", "sum"),
    )
    .reset_index()
)

for col in ["excluded_bcs", "internal_removals", "deprecated_removals"]:
    flags[f"{col}_share"] = (flags[col] / flags["total_bcs"].replace(0, np.nan)).fillna(0)

flag_plot = flags.sort_values("total_bcs", ascending=False)
long_flag = flag_plot.melt(
    id_vars=["library", "total_bcs"],
    value_vars=["excluded_bcs_share", "internal_removals_share", "deprecated_removals_share"],
    var_name="metric",
    value_name="share",
)

name_map = {
    "excluded_bcs_share": "Excluded symbol BC share",
    "internal_removals_share": "Internal removal share",
    "deprecated_removals_share": "Deprecated-removal share",
}
long_flag["metric"] = long_flag["metric"].map(name_map)

plt.figure(figsize=(20, 8))
sns.barplot(data=long_flag, x="library", y="share", hue="metric")
plt.title("Excluded/internal/deprecated-removal ratios by library")
plt.xlabel("Library")
plt.ylabel("Share of breaking-change events")
plt.xticks(rotation=70, ha="right")
plt.tight_layout()
plt.show()

flags.sort_values("excluded_bcs_share", ascending=False).head(10)

vis = (
    bcs_df.groupby(["library", "symbol_visibility"]).size().rename("count").reset_index()
)
vis["share"] = vis.groupby("library")["count"].transform(lambda s: s / s.sum())

top_libs = coverage.sort_values("bc_rows", ascending=False).head(10).index
vis_plot = vis[vis["library"].isin(top_libs)]

plt.figure(figsize=(18, 8))
sns.barplot(data=vis_plot, x="library", y="share", hue="symbol_visibility")
plt.title("Visibility of impacted symbols in breaking changes")
plt.xlabel("Library")
plt.ylabel("Share")
plt.xticks(rotation=65, ha="right")
plt.tight_layout()
plt.show()

monthly_commits = commits_df.copy()
monthly_commits["month"] = monthly_commits["date_utc"].dt.tz_convert(None).dt.to_period("M").astype(str)

monthly = monthly_commits.groupby(["library", "month"]).agg(
    monthly_commits=("commit_sha", "count"),
    monthly_breaks=("breaking_changes_count", "sum"),
    monthly_abs_churn=("abs_loc_churn", "sum"),
).reset_index()
monthly["breaks_per_100_commits"] = (monthly["monthly_breaks"] / monthly["monthly_commits"].replace(0, np.nan) * 100).fillna(0)

# Heatmap of monthly break intensity for most active libraries
active_libs = coverage.sort_values("commits", ascending=False).index
heat = monthly[monthly["library"].isin(active_libs)].pivot(index="library", columns="month", values="breaks_per_100_commits").fillna(0)

plt.figure(figsize=(22, 18))
sns.heatmap(np.log1p(heat), cmap="rocket_r", cbar_kws={"label": "log(1 + breaks per 100 commits)"})
plt.title("Temporal break intensity (most active libraries)")
plt.xlabel("Month")
plt.ylabel("Library")
plt.tight_layout()
plt.show()

# Pareto concentration: how many commits explain 80% of breaking changes in each library
pareto_rows = []
for lib, d in commits_df.groupby("library"):
    s = d["breaking_changes_count"].sort_values(ascending=False).reset_index(drop=True)
    total = s.sum()
    if total <= 0:
        pareto_rows.append({"library": lib, "commits_for_80pct_breaks": np.nan, "total_commits": len(d)})
        continue
    csum = s.cumsum()
    needed = int((csum < (0.8 * total)).sum() + 1)
    pareto_rows.append({"library": lib, "commits_for_80pct_breaks": needed, "total_commits": len(d)})

pareto = pd.DataFrame(pareto_rows)
pareto["share_of_commits_for_80pct_breaks"] = (
    pareto["commits_for_80pct_breaks"] / pareto["total_commits"].replace(0, np.nan)
)
pareto = pareto.sort_values("share_of_commits_for_80pct_breaks")

plt.figure(figsize=(16, 7))
sns.barplot(data=pareto.dropna(subset=["share_of_commits_for_80pct_breaks"]), x="library", y="share_of_commits_for_80pct_breaks", color="#457b9d")
plt.title("Concentration of breaking changes (lower means more concentrated)")
plt.xlabel("Library")
plt.ylabel("Commit share needed to accumulate 80% of breaks")
plt.xticks(rotation=70, ha="right")
plt.tight_layout()
plt.show()

pareto.head(15)

pkg_hotspots = (
    bcs_df.dropna(subset=["impacted_package_fqn"]) 
    .groupby(["library", "impacted_package_fqn"]).size().rename("count").reset_index()
    .sort_values("count", ascending=False)
)

type_hotspots = (
    bcs_df.dropna(subset=["impacted_type_fqn"]) 
    .groupby(["library", "impacted_type_fqn"]).size().rename("count").reset_index()
    .sort_values("count", ascending=False)
)

print("Top impacted packages across all libraries:")
display(pkg_hotspots.head(20))

print("Top impacted types across all libraries:")
display(type_hotspots.head(20))

Top impacted packages across all libraries:

Top impacted types across all libraries:

summary = coverage.reset_index().merge(
    flags[["library", "excluded_bcs_share", "internal_removals_share", "deprecated_removals_share"]],
    on="library",
    how="left",
).merge(
    pareto[["library", "share_of_commits_for_80pct_breaks"]],
    on="library",
    how="left",
)

summary["breaks_per_1k_final_exported"] = (
    summary["total_reported_breaks"] / summary["final_exported_symbols"].replace(0, np.nan) * 1000
).fillna(0)

summary = summary.sort_values(["total_reported_breaks", "commits"], ascending=[False, False])
summary.head(25)

# Link BC rows to commit-level context
commit_context_cols = [
    "library", "commit_sha", "date_utc", "is_merge_commit", "has_java_changes", "has_pom_changes",
    "files_changed", "abs_loc_churn", "days_since_prev_commit", "breaking_changes_count",
    "binary_breaking_changes_count", "source_breaking_changes_count", "tag", "version", "branch",
    "exported_symbols_count", "internal_share", "deprecated_share",
]

commit_ctx = commits_df[commit_context_cols].copy()
commit_ctx = commit_ctx.rename(columns={"commit_sha": "commit"})

bcs_enriched = bcs_df.merge(commit_ctx, on=["library", "commit"], how="left", validate="many_to_one")

# Commit-level BC event counts from row-level table
bc_rows_per_commit = (
    bcs_enriched.groupby(["library", "commit"]).size().rename("bc_rows").reset_index()
)

commit_enriched = commit_ctx.merge(bc_rows_per_commit, on=["library", "commit"], how="left")
commit_enriched["bc_rows"] = commit_enriched["bc_rows"].fillna(0)
commit_enriched["has_bc_rows"] = commit_enriched["bc_rows"] > 0

# Useful derived features
commit_enriched["is_tagged_commit"] = commit_enriched["tag"].notna() | commit_enriched["version"].notna()
commit_enriched["binary_share_in_commit"] = (
    commit_enriched["binary_breaking_changes_count"] /
    commit_enriched["breaking_changes_count"].replace(0, np.nan)
).fillna(0)

print("Enriched BC rows:", len(bcs_enriched))
print("Commits with at least one BC row:", int(commit_enriched["has_bc_rows"].sum()))
print("Share of commits with BC rows:", round(commit_enriched["has_bc_rows"].mean(), 4))

Enriched BC rows: 658235
Commits with at least one BC row: 13868
Share of commits with BC rows: 0.0948

# Compare contexts: breaking vs non-breaking commits
context_summary = commit_enriched.groupby("has_bc_rows").agg(
    commits=("commit", "count"),
    median_files_changed=("files_changed", "median"),
    median_abs_churn=("abs_loc_churn", "median"),
    median_days_since_prev=("days_since_prev_commit", "median"),
    merge_rate=("is_merge_commit", "mean"),
    java_change_rate=("has_java_changes", "mean"),
    pom_change_rate=("has_pom_changes", "mean"),
    tagged_commit_rate=("is_tagged_commit", "mean"),
).reset_index()

context_summary["has_bc_rows"] = context_summary["has_bc_rows"].map({False: "No BC", True: "Has BC"})
context_summary

# Break probability as a function of churn and inactivity
work = commit_enriched.copy()
work["churn_decile"] = pd.qcut(
    work["abs_loc_churn"].rank(method="first"),
    q=10,
    labels=[f"D{i}" for i in range(1, 11)]
)
work["inactivity_bucket"] = pd.cut(
    work["days_since_prev_commit"],
    bins=[-0.1, 0, 1, 3, 7, 30, 365, np.inf],
    labels=["0d", "1d", "2-3d", "4-7d", "8-30d", "31-365d", ">365d"],
)

p1 = work.groupby("churn_decile", observed=False)["has_bc_rows"].mean().reset_index(name="break_commit_rate")
p2 = work.groupby("inactivity_bucket", observed=False)["has_bc_rows"].mean().reset_index(name="break_commit_rate")

fig, axes = plt.subplots(1, 2, figsize=(16, 6))
sns.barplot(data=p1, x="churn_decile", y="break_commit_rate", color="#e76f51", ax=axes[0])
axes[0].set_title("Probability a commit has BCs by churn decile")
axes[0].set_xlabel("Churn decile")
axes[0].set_ylabel("P(commit has BC rows)")

sns.barplot(data=p2, x="inactivity_bucket", y="break_commit_rate", color="#264653", ax=axes[1])
axes[1].set_title("Probability a commit has BCs by inactivity")
axes[1].set_xlabel("Days since previous commit")
axes[1].set_ylabel("P(commit has BC rows)")

plt.tight_layout()
plt.show()

def nearest_release_distance_days(lib_df: pd.DataFrame) -> pd.Series:
    d = lib_df.sort_values("date_utc").copy()
    release_dates = d.loc[d["tag"].notna() | d["version"].notna(), "date_utc"].drop_duplicates().sort_values()

    if release_dates.empty:
        return pd.Series(np.nan, index=d.index)

    release_ns = release_dates.astype("int64").to_numpy()
    commit_ns = d["date_utc"].astype("int64").to_numpy()
    idx = np.searchsorted(release_ns, commit_ns)

    left_idx = np.clip(idx - 1, 0, len(release_ns) - 1)
    right_idx = np.clip(idx, 0, len(release_ns) - 1)

    left_dist = np.abs(commit_ns - release_ns[left_idx])
    right_dist = np.abs(commit_ns - release_ns[right_idx])
    min_dist_days = np.minimum(left_dist, right_dist) / 1e9 / 86400

    out = pd.Series(min_dist_days, index=d.index)
    return out.reindex(lib_df.index)


commit_enriched["days_to_nearest_release"] = np.nan
for _lib, _idx in commit_enriched.groupby("library").groups.items():
    commit_enriched.loc[_idx, "days_to_nearest_release"] = nearest_release_distance_days(commit_enriched.loc[_idx]).values

release_bins = [-0.1, 0, 1, 3, 7, 30, 90, 365, np.inf]
release_labels = ["release day", "1d", "2-3d", "4-7d", "8-30d", "31-90d", "91-365d", ">365d"]

commit_enriched["release_proximity"] = pd.cut(
    commit_enriched["days_to_nearest_release"], bins=release_bins, labels=release_labels
)

release_effect = commit_enriched.groupby("release_proximity", observed=False).agg(
    commits=("commit", "count"),
    break_commit_rate=("has_bc_rows", "mean"),
    mean_breaks_per_commit=("bc_rows", "mean"),
).reset_index()

release_effect

fig, axes = plt.subplots(1, 2, figsize=(17, 6))

sns.barplot(data=release_effect, x="release_proximity", y="break_commit_rate", color="#2a9d8f", ax=axes[0])
axes[0].set_title("Break-commit rate by distance to nearest release marker")
axes[0].set_xlabel("Distance to nearest release/tag commit")
axes[0].set_ylabel("P(commit has BC rows)")
axes[0].tick_params(axis="x", rotation=30)

sns.barplot(data=release_effect, x="release_proximity", y="mean_breaks_per_commit", color="#f4a261", ax=axes[1])
axes[1].set_title("Mean BC rows per commit by release proximity")
axes[1].set_xlabel("Distance to nearest release/tag commit")
axes[1].set_ylabel("Mean BC rows per commit")
axes[1].tick_params(axis="x", rotation=30)

plt.tight_layout()
plt.show()

def infer_intent(row):
    tag = str(row.get("conventional_commit_tag", "") or "").strip().lower()
    msg = str(row.get("commit_short_msg", "") or "").strip().lower()
    text = f"{tag} {msg}"

    rules = [
        ("release", ["release", "version", "bump version", "prepare", "tag"]),
        ("revert", ["revert"]),
        ("deps", ["dependenc", "upgrade", "bump", "renovate"]),
        ("build", ["pom", "gradle", "maven", "build", "ci", "workflow"]),
        ("docs", ["readme", "doc", "javadoc", "documentation"]),
        ("test", ["test", "assert", "spec"]),
        ("fix", ["fix", "bug", "issue", "patch", "hotfix"]),
        ("refactor", ["refactor", "cleanup", "simplify", "rename"]),
        ("feature", ["feat", "feature", "add", "introduce", "implement"]),
        ("breaking", ["breaking", "remove", "drop", "deprecat", "api change"]),
    ]

    for label, kws in rules:
        if any(k in text for k in kws):
            return label
    return "other"


intent_df = commit_enriched.merge(
    commits_df[["library", "commit_sha", "commit_short_msg", "conventional_commit_tag"]],
    left_on=["library", "commit"],
    right_on=["library", "commit_sha"],
    how="left",
)

intent_df["intent"] = intent_df.apply(infer_intent, axis=1)

intent_stats = intent_df.groupby(["library", "intent"]).agg(
    commits=("commit", "count"),
    break_commit_rate=("has_bc_rows", "mean"),
    mean_bc_rows=("bc_rows", "mean"),
).reset_index()

intent_stats["intent_share"] = intent_stats.groupby("library")["commits"].transform(lambda s: s / s.sum())

intent_stats.head(20)

# Evolution style map: intent composition (share) + policy map (break rate by intent)
selected_intents = ["feature", "fix", "refactor", "deps", "build", "release", "breaking", "docs", "test", "other"]
plot_intent = intent_stats[intent_stats["intent"].isin(selected_intents)].copy()

heat_share = plot_intent.pivot(index="library", columns="intent", values="intent_share").fillna(0)
heat_break_rate = plot_intent.pivot(index="library", columns="intent", values="break_commit_rate").fillna(0)

lib_order = coverage.sort_values("commits", ascending=False).index
heat_share = heat_share.reindex(lib_order)
heat_break_rate = heat_break_rate.reindex(lib_order)

fig, axes = plt.subplots(1, 2, figsize=(22, 10))
sns.heatmap(heat_share, cmap="Blues", ax=axes[0], cbar_kws={"label": "Share of commits"})
axes[0].set_title("Intent composition by library")
axes[0].set_xlabel("Intent")
axes[0].set_ylabel("Library")

sns.heatmap(heat_break_rate, cmap="Reds", ax=axes[1], cbar_kws={"label": "P(commit has BC rows)"})
axes[1].set_title("Break propensity by intent and library")
axes[1].set_xlabel("Intent")
axes[1].set_ylabel("")

plt.tight_layout()
plt.show()

# Build profile features leveraging both commits and BC rows
nature_stats = bcs_df.groupby(["library", "nature"]).size().unstack(fill_value=0)
kind_diversity = bcs_df.groupby("library")["kind"].nunique().rename("bc_kind_diversity")
visibility_public_share = (
    bcs_df.assign(is_public=bcs_df["symbol_visibility"].eq("public"))
    .groupby("library")["is_public"].mean()
    .rename("public_visibility_share")
)

monthly_break_vol = (
    commits_df.assign(month=commits_df["date_utc"].dt.tz_convert(None).dt.to_period("M").astype(str))
    .groupby(["library", "month"])["breaking_changes_count"].sum()
    .groupby("library").std()
    .fillna(0)
    .rename("monthly_break_std")
)

profile = commit_enriched.groupby("library").agg(
    commits=("commit", "count"),
    share_break_commits=("has_bc_rows", "mean"),
    mean_bc_rows_per_commit=("bc_rows", "mean"),
    median_churn=("abs_loc_churn", "median"),
    median_churn_break_commits=("abs_loc_churn", lambda s: s[commit_enriched.loc[s.index, "has_bc_rows"]].median() if commit_enriched.loc[s.index, "has_bc_rows"].any() else 0),
    merge_rate=("is_merge_commit", "mean"),
    tagged_commit_rate=("is_tagged_commit", "mean"),
    pom_change_rate=("has_pom_changes", "mean"),
    java_change_rate=("has_java_changes", "mean"),
    median_days_since_prev=("days_since_prev_commit", "median"),
    mean_internal_share=("internal_share", "mean"),
    mean_deprecated_share=("deprecated_share", "mean"),
    mean_binary_share_per_breaking_commit=("binary_share_in_commit", "mean"),
).join(flags.set_index("library")[["excluded_bcs_share", "internal_removals_share", "deprecated_removals_share"]], how="left")

profile = profile.join(kind_diversity, how="left")
profile = profile.join(visibility_public_share, how="left")
profile = profile.join(monthly_break_vol, how="left")

for col in ["deletion", "mutation", "addition"]:
    if col not in nature_stats.columns:
        nature_stats[col] = 0
nature_shares = nature_stats[["deletion", "mutation", "addition"]].div(nature_stats.sum(axis=1).replace(0, np.nan), axis=0).fillna(0)
nature_shares.columns = ["nature_deletion_share", "nature_mutation_share", "nature_addition_share"]
profile = profile.join(nature_shares, how="left")

profile["bc_per_100_commits"] = profile["mean_bc_rows_per_commit"] * 100
profile["break_churn_multiplier"] = profile["median_churn_break_commits"] / profile["median_churn"].replace(0, np.nan)
profile["break_churn_multiplier"] = profile["break_churn_multiplier"].replace([np.inf, -np.inf], np.nan).fillna(0)

profile.head(20)

# Profile map via SVD on standardized features (no external ML deps)
feature_cols = [
    "share_break_commits", "bc_per_100_commits", "merge_rate", "tagged_commit_rate", "pom_change_rate",
    "mean_internal_share", "mean_deprecated_share", "excluded_bcs_share", "internal_removals_share",
    "deprecated_removals_share", "bc_kind_diversity", "public_visibility_share", "monthly_break_std",
    "nature_deletion_share", "nature_mutation_share", "nature_addition_share", "break_churn_multiplier",
]

X = profile[feature_cols].copy().fillna(0)
Xz = (X - X.mean(axis=0)) / X.std(axis=0).replace(0, 1)
U, S, Vt = np.linalg.svd(Xz.values, full_matrices=False)
coords = pd.DataFrame(U[:, :2] * S[:2], index=Xz.index, columns=["profile_x", "profile_y"])

profile_map = profile.join(coords)

plt.figure(figsize=(14, 10))
sns.scatterplot(
    data=profile_map.reset_index(),
    x="profile_x",
    y="profile_y",
    size="bc_per_100_commits",
    hue="share_break_commits",
    palette="viridis",
    sizes=(50, 500),
    alpha=0.85,
)
for row in profile_map.reset_index().itertuples(index=False):
    plt.text(row.profile_x, row.profile_y, row.library, fontsize=9, alpha=0.85)

plt.title("Library profile map (dimension-reduced style/policy features)")
plt.xlabel("Profile axis 1")
plt.ylabel("Profile axis 2")
plt.legend(bbox_to_anchor=(1.02, 1), loc="upper left")
plt.tight_layout()
plt.show()

# Z-score comparison heatmap across all libraries
profile_z = Xz.loc[coverage.sort_values("commits", ascending=False).index]

plt.figure(figsize=(20, max(10, 0.45 * len(profile_z))))
sns.heatmap(profile_z, cmap="coolwarm", center=0, cbar_kws={"label": "Feature z-score"})
plt.title("Comparative profile heatmap (all libraries)")
plt.xlabel("Profile features")
plt.ylabel("Library")
plt.tight_layout()
plt.show()

def hhi_from_counts(counts: pd.Series) -> float:
    total = counts.sum()
    if total <= 0:
        return np.nan
    shares = counts / total
    return float((shares ** 2).sum())

pkg_conc = bcs_df.groupby(["library", "impacted_package_fqn"]).size().rename("count").reset_index()

pkg_hhi = pkg_conc.groupby("library")["count"].apply(hhi_from_counts).rename("package_hhi")
pkg_unique = pkg_conc.groupby("library")["impacted_package_fqn"].nunique().rename("unique_impacted_packages")

type_conc = bcs_df.groupby(["library", "impacted_type_fqn"]).size().rename("count").reset_index()
type_hhi = type_conc.groupby("library")["count"].apply(hhi_from_counts).rename("type_hhi")
type_unique = type_conc.groupby("library")["impacted_type_fqn"].nunique().rename("unique_impacted_types")

conc = (
    coverage[["bc_rows"]]
    .join(pkg_hhi, how="left")
    .join(pkg_unique, how="left")
    .join(type_hhi, how="left")
    .join(type_unique, how="left")
    .reset_index()
)

fig, axes = plt.subplots(1, 2, figsize=(16, 6))

sns.scatterplot(
    data=conc,
    x="bc_rows",
    y="package_hhi",
    size="unique_impacted_packages",
    hue="unique_impacted_packages",
    palette="mako",
    sizes=(30, 350),
    ax=axes[0],
)
axes[0].set_xscale("log")
axes[0].set_title("Package concentration vs BC volume")
axes[0].set_xlabel("BC rows (log scale)")
axes[0].set_ylabel("HHI of impacted package distribution")

sns.scatterplot(
    data=conc,
    x="bc_rows",
    y="type_hhi",
    size="unique_impacted_types",
    hue="unique_impacted_types",
    palette="crest",
    sizes=(30, 350),
    ax=axes[1],
)
axes[1].set_xscale("log")
axes[1].set_title("Type concentration vs BC volume")
axes[1].set_xlabel("BC rows (log scale)")
axes[1].set_ylabel("HHI of impacted type distribution")

plt.tight_layout()
plt.show()

conc.sort_values("package_hhi", ascending=False).head(15)

# Public/protected + excluded/internal interaction matrix by kind
interaction = bcs_df.copy()
interaction["group"] = np.select(
    [
        interaction["is_internal_removal"] & interaction["is_excluded_symbol"],
        interaction["is_internal_removal"],
        interaction["is_excluded_symbol"],
        interaction["is_deprecated_removal"],
    ],
    ["internal+excluded", "internal", "excluded", "deprecated-removal"],
    default="regular",
)

top_kinds = interaction["kind"].value_counts().index
mat = (
    interaction[interaction["kind"].isin(top_kinds)]
    .groupby(["kind", "group"]).size().rename("count").reset_index()
)
mat["share"] = mat.groupby("kind")["count"].transform(lambda s: s / s.sum())
heat = mat.pivot(index="kind", columns="group", values="share").fillna(0)

plt.figure(figsize=(12, 12))
sns.heatmap(heat, cmap="OrRd", annot=True, fmt=".2f", cbar_kws={"label": "Share within kind"})
plt.xticks(rotation=90)
plt.title("How BC kinds split across regular/excluded/internal/deprecated groups")
plt.xlabel("BC group")
plt.ylabel("BC kind")
plt.tight_layout()
plt.show()

LIB_TO_INSPECT = "guava"  # change as needed

dc = commits_df[commits_df["library"] == LIB_TO_INSPECT].sort_values("date_utc").copy()
db = bcs_enriched[bcs_enriched["library"] == LIB_TO_INSPECT].copy()

if dc.empty:
    print(f"Library {LIB_TO_INSPECT} not found.")
else:
    fig, axes = plt.subplots(2, 2, figsize=(18, 11))

    axes[0, 0].plot(dc["date_utc"], dc["exported_symbols_count"], color="#1d3557", label="Exported")
    axes[0, 0].plot(dc["date_utc"], dc["internal_count"], color="#2a9d8f", label="Internal")
    axes[0, 0].set_title(f"{LIB_TO_INSPECT}: API size timeline")
    axes[0, 0].legend()

    axes[0, 1].plot(dc["date_utc"], dc["breaking_changes_count"].rolling(60, min_periods=5).mean(), color="#e76f51")
    axes[0, 1].set_title(f"{LIB_TO_INSPECT}: rolling BC count (60 commits)")

    kind_counts = db["kind"].value_counts().head(10)
    sns.barplot(x=kind_counts.values, y=kind_counts.index, ax=axes[1, 0], color="#457b9d")
    axes[1, 0].set_title("Top BC kinds")
    axes[1, 0].set_xlabel("Count")
    axes[1, 0].set_ylabel("")

    comp_counts = db["compatibility"].value_counts(dropna=False)
    axes[1, 1].pie(comp_counts.values, labels=comp_counts.index, autopct="%.1f%%")
    axes[1, 1].set_title("Compatibility split")

    plt.tight_layout()
    plt.show()

	commits	first_commit	last_commit	commits_with_breaks	total_reported_breaks	final_exported_symbols	final_internal_symbols	merge_commit_rate	java_change_rate	bc_rows	bc_count_delta
library
assertj-core	3672	2010-09-07 04:06:36+00:00	2026-02-07 22:12:04+00:00	1001	230771	6932	85	0.049564	0.512527	230771	0
jackson-databind	6582	2011-12-23 08:31:35+00:00	2026-02-08 04:52:24+00:00	2007	145244	9122	0	0.421908	0.822546	145244	0
rxjava-core	3499	2013-01-09 06:21:43+00:00	2026-02-06 08:29:11+00:00	541	128110	4254	1850	0.335810	0.661332	128110	0
hibernate-core	4826	2010-10-11 19:41:47+00:00	2016-08-10 05:41:04+00:00	846	34244	25810	9464	0.016162	0.846042	34244	0
h2-database	8024	2006-12-15 00:12:44+00:00	2026-01-31 05:09:18+00:00	1384	34007	10719	0	0.192547	0.871386	34007	0
tomcat	27700	2006-03-27 13:53:46+00:00	2026-02-06 22:39:49+00:00	3287	33514	23836	0	0.002310	0.750433	33514	0
commons-collections	4856	2001-04-14 15:38:58+00:00	2026-02-06 14:23:17+00:00	406	9963	3713	0	0.022035	0.678336	9963	0
jackson-core	2572	2011-12-23 07:00:40+00:00	2026-02-07 21:49:29+00:00	424	7384	3002	0	0.422628	0.683904	7384	0
joda-time	2132	2003-12-16 21:39:27+00:00	2026-01-21 20:45:38+00:00	178	3676	3045	0	0.043152	0.568011	3676	0
netty-codec-http	9661	2011-12-28 10:44:04+00:00	2026-02-06 10:10:55+00:00	178	3392	2654	0	0.008281	0.840182	3392	0
commons-pool	2804	2001-04-14 16:40:29+00:00	2026-02-06 14:39:30+00:00	240	3350	609	0	0.016762	0.529601	3350	0
httpcomponents-client	3170	2009-03-01 16:36:52+00:00	2026-02-07 18:00:09+00:00	264	3116	2382	77	0.004416	0.782334	3116	0
commons-beanutils	2196	2001-03-27 05:25:57+00:00	2026-02-06 14:21:23+00:00	133	2285	758	0	0.013661	0.518215	2285	0
commons-lang	8614	2002-07-19 03:35:56+00:00	2026-02-07 20:01:43+00:00	396	2274	4284	0	0.024379	0.717088	2274	0
guava	6972	2011-04-15 17:22:23+00:00	2026-02-07 00:34:41+00:00	378	2037	5074	39	0.000143	0.897734	2037	0
fastjson2-core	4597	2022-04-17 05:16:05+00:00	2026-02-08 00:22:56+00:00	367	2000	4910	452	0.048727	0.774636	2000	0
fastjson-core	2934	2011-07-31 12:05:24+00:00	2023-05-12 06:16:03+00:00	322	1829	2124	0	0.140082	0.914110	1829	0
log4j-api	9835	2013-08-26 12:21:54+00:00	2026-01-22 10:08:42+00:00	145	1546	2200	90	0.032028	0.614540	1546	0
commons-compress	5436	2003-11-23 20:07:47+00:00	2026-02-06 14:23:42+00:00	213	1370	3706	27	0.017476	0.733996	1370	0
commons-io	5560	2002-01-26 02:47:42+00:00	2026-02-07 21:09:27+00:00	187	1209	2505	0	0.016187	0.680576	1209	0

	library	total_bcs	excluded_bcs	internal_removals	deprecated_removals	excluded_bcs_share	internal_removals_share	deprecated_removals_share
32	rxjava-core	128110	100935	2773	1879	0.787878	0.021645	0.014667
15	gson	470	353	121	0	0.751064	0.257447	0.000000
16	guava	2037	1488	189	278	0.730486	0.092784	0.136475
19	hibernate-core	34244	5369	2727	730	0.156787	0.079634	0.021318
14	fastjson2-core	2000	151	137	3	0.075500	0.068500	0.001500
1	assertj-core	230771	9699	6993	1397	0.042029	0.030303	0.006054
28	log4j-api	1546	64	12	1	0.041397	0.007762	0.000647
20	httpcomponents-client	3116	124	22	214	0.039795	0.007060	0.068678
18	hamcrest-core	435	8	8	1	0.018391	0.018391	0.002299
27	jsoup	919	14	8	51	0.015234	0.008705	0.055495

	library	commits_for_80pct_breaks	total_commits	share_of_commits_for_80pct_breaks
0	JSON-java	1	389	0.002571
28	log4j-api	26	9835	0.002644
24	jakartaee-servlet-api	2	553	0.003617
29	netty-codec-http	43	9661	0.004451
12	commons-text	14	2322	0.006029
30	protobuf-java	10	1151	0.008688
4	commons-cli	16	1838	0.008705
8	commons-io	50	5560	0.008993
7	commons-compress	59	5436	0.010854
10	commons-logging	21	1826	0.011501
3	commons-beanutils	26	2196	0.011840
5	commons-codec	41	3172	0.012926
23	jakartaee-jaxrs-api	5	380	0.013158
6	commons-collections	65	4856	0.013386
33	slf4j-api	22	1638	0.013431

	library	impacted_package_fqn	count
77	assertj-core	org.assertj.core.api	180600
1215	jackson-databind	com.fasterxml.jackson.databind.deser.std	57955
1371	rxjava-core	io.reactivex.internal.operators.observable	39001
1367	rxjava-core	io.reactivex.internal.operators.flowable	27820
1402	rxjava-core	io.reactivex.rxjava3.internal.operators.flowable	12002
1210	jackson-databind	com.fasterxml.jackson.databind.deser	11785
1247	jackson-databind	tools.jackson.databind.deser.jdk	10886
1212	jackson-databind	com.fasterxml.jackson.databind.deser.impl	8228
1091	hibernate-core	org.hibernate.type	7595
1217	jackson-databind	com.fasterxml.jackson.databind.ext	7092
1447	rxjava-core	rx.subjects	6323
278	assertj-core	org.fest.assertions.api	6216
1235	jackson-databind	com.fasterxml.jackson.databind.ser.std	5951
1420	rxjava-core	io.reactivex.subjects	5095
715	h2-database	org.h2.value	4518
1373	rxjava-core	io.reactivex.internal.operators.single	4395
220	assertj-core	org.assertj.core.condition	4086
1366	rxjava-core	io.reactivex.internal.operators.completable	3793
128	assertj-core	org.assertj.core.api.objectarray	3595
1219	jackson-databind	com.fasterxml.jackson.databind.ext.jdk8	3207

	library	impacted_type_fqn	count
1764	assertj-core	org.assertj.core.api.BDDAssertions	6043
1646	assertj-core	org.assertj.core.api.Assertions	4219
20579	jackson-databind	com.fasterxml.jackson.databind.deser.BeanDeser...	3500
20852	jackson-databind	com.fasterxml.jackson.databind.deser.std.Throw...	3421
2029	assertj-core	org.assertj.core.api.WithAssertions	2934
20585	jackson-databind	com.fasterxml.jackson.databind.deser.BuilderBa...	2911
20580	jackson-databind	com.fasterxml.jackson.databind.deser.BeanDeser...	2726
1597	assertj-core	org.assertj.core.api.AbstractIterableAssert	2710
1600	assertj-core	org.assertj.core.api.AbstractListAssert	2648
20649	jackson-databind	com.fasterxml.jackson.databind.deser.impl.Bean...	2601
1952	assertj-core	org.assertj.core.api.ObjectArrayAssert	2530
20648	jackson-databind	com.fasterxml.jackson.databind.deser.impl.Bean...	2492
1824	assertj-core	org.assertj.core.api.ConcreteIterableAssert	2472
1892	assertj-core	org.assertj.core.api.IterableAssert	2395
1925	assertj-core	org.assertj.core.api.ListAssert	2323
1610	assertj-core	org.assertj.core.api.AbstractObjectArrayAssert	2302
1855	assertj-core	org.assertj.core.api.FactoryBasedNavigableIter...	1939
1811	assertj-core	org.assertj.core.api.ClassBasedNavigableIterab...	1938
1856	assertj-core	org.assertj.core.api.FactoryBasedNavigableList...	1906
1911	assertj-core	org.assertj.core.api.Java6Assertions	1889

API Evolution and Breaking Changes Analysis¶

Data Quality and Coverage¶

Per-Library Timeline: API Size and Breaking Changes¶

API Evolution and Break Risk¶

Breaking-Change Taxonomy¶

Excluded, Internal, and Deprecated-Removal Signals¶

Temporal Patterns and Concentration¶

Hotspots in Impacted Packages and Types¶

Consolidated Summary Table¶

Commit Context of Breaking Changes¶

Release/Tag Proximity Effects¶

Commit Intent and Evolution Style¶

Library Profiles and Comparative Mapping¶

Where Breaking Changes Concentrate¶

Optional: Per-Library Deep Dive Helper¶

	has_bc_rows	commits	median_files_changed	median_abs_churn	median_days_since_prev	merge_rate	java_change_rate	pom_change_rate	tagged_commit_rate
0	No BC	132466	1.0	14.0	0.0	0.071226	0.677593	0.115803	0.009361
1	Has BC	13868	5.0	133.0	0.0	0.135203	1.000000	0.024445	0.001947

	release_proximity	commits	break_commit_rate	mean_breaks_per_commit
0	release day	1277	0.021143	2.000000
1	1d	7766	0.070306	3.789596
2	2-3d	6090	0.105911	6.803777
3	4-7d	8765	0.098688	6.581289
4	8-30d	19751	0.098274	9.893778
5	31-90d	15486	0.104223	9.643936
6	91-365d	19885	0.059844	2.670405
7	>365d	39614	0.094739	2.417277

	library	intent	commits	break_commit_rate	mean_bc_rows	intent_share
0	JSON-java	breaking	7	0.142857	0.142857	0.017995
1	JSON-java	build	21	0.047619	7.142857	0.053985
2	JSON-java	deps	2	0.000000	0.000000	0.005141
3	JSON-java	docs	42	0.000000	0.000000	0.107969
4	JSON-java	feature	7	0.142857	0.428571	0.017995
5	JSON-java	fix	66	0.030303	0.060606	0.169666
6	JSON-java	other	181	0.000000	0.000000	0.465296
7	JSON-java	refactor	6	0.166667	0.500000	0.015424
8	JSON-java	release	27	0.000000	0.000000	0.069409
9	JSON-java	revert	6	0.166667	2.500000	0.015424
10	JSON-java	test	24	0.000000	0.000000	0.061697
11	assertj-core	breaking	106	0.415094	67.849057	0.028867
12	assertj-core	build	169	0.248521	86.201183	0.046024
13	assertj-core	deps	753	0.007968	17.540505	0.205065
14	assertj-core	docs	231	0.290043	77.510823	0.062908
15	assertj-core	feature	122	0.319672	62.647541	0.033224
16	assertj-core	fix	266	0.421053	56.755639	0.072440
17	assertj-core	other	426	0.415493	163.873239	0.116013
18	assertj-core	refactor	67	0.597015	55.313433	0.018246
19	assertj-core	release	643	0.024883	11.555210	0.175109

	library	bc_rows	package_hhi	unique_impacted_packages	type_hhi	unique_impacted_types
33	JSON-java	176	1.000000	1	0.118221	15
23	protobuf-java	562	1.000000	1	0.055426	54
26	hamcrest-core	435	0.691552	4	0.053687	51
0	assertj-core	230771	0.614291	354	0.004927	10189
24	gson	470	0.446781	8	0.068139	103
27	jakartaee-validation	416	0.316753	11	0.018618	161
31	slf4j-api	249	0.314559	5	0.053370	49
8	joda-time	3676	0.308485	12	0.012665	233
28	commons-logging	361	0.305975	18	0.031177	110
10	commons-pool	3350	0.278548	12	0.024256	228
17	log4j-api	1546	0.273850	9	0.110659	131
9	netty-codec-http	3392	0.266669	7	0.012840	226
22	jsoup	919	0.238523	11	0.039584	146
15	fastjson2-core	2000	0.232882	26	0.023001	259
34	jakartaee-servlet-api	131	0.231047	7	0.018938	97

	commits	share_break_commits	mean_bc_rows_per_commit	median_churn	median_churn_break_commits	merge_rate	tagged_commit_rate	pom_change_rate	java_change_rate	median_days_since_prev	mean_internal_share	mean_deprecated_share	mean_binary_share_per_breaking_commit	excluded_bcs_share	internal_removals_share	deprecated_removals_share	bc_kind_diversity	public_visibility_share	monthly_break_std	nature_deletion_share	nature_mutation_share	nature_addition_share	bc_per_100_commits	break_churn_multiplier
library
JSON-java	389	0.017995	0.452442	24.0	692.0	0.658098	0.064267	0.084833	0.735219	4.0	0.000000	0.000275	0.015544	0.000000	0.000000	0.000000	7	0.982955	13.581015	0.159091	0.840909	0.000000	45.244216	28.833333
assertj-core	3672	0.272603	62.846133	10.0	261.0	0.049564	0.016885	0.395969	0.512527	0.0	0.179138	0.007116	0.255184	0.042029	0.030303	0.006054	24	0.875786	2444.442170	0.592410	0.389741	0.017849	6284.613290	26.100000
awaitility	630	0.063492	0.415873	6.0	199.5	0.057143	0.060317	0.325397	0.298413	0.0	0.000000	0.000334	0.050452	0.000000	0.000000	0.003817	14	1.000000	9.565623	0.648855	0.297710	0.053435	41.587302	33.250000
commons-beanutils	2196	0.060565	1.040528	8.0	75.0	0.013661	0.000455	0.141166	0.518215	0.0	0.000000	0.010436	0.053713	0.000000	0.000000	0.041575	21	0.820569	53.498194	0.466083	0.525602	0.008315	104.052823	9.375000
commons-cli	1838	0.047334	0.577802	7.0	120.0	0.026115	0.001632	0.152884	0.431447	0.0	0.000000	0.049088	0.034920	0.000000	0.000000	0.000000	21	0.953861	36.877658	0.715631	0.245763	0.038606	57.780196	17.142857
commons-codec	3172	0.046028	0.293821	8.0	69.5	0.018600	0.001892	0.139029	0.559269	0.0	0.000000	0.058108	0.038974	0.000000	0.000000	0.008584	16	0.907725	20.824764	0.680258	0.313305	0.006438	29.382093	8.687500
commons-collections	4856	0.083608	2.051689	14.0	108.0	0.022035	0.001030	0.091639	0.678336	0.0	0.000000	0.003226	0.070279	0.000000	0.000000	0.001807	25	0.821841	316.188783	0.430192	0.552645	0.017164	205.168863	7.714286
commons-compress	5436	0.039183	0.252024	10.0	79.0	0.017476	0.001104	0.093635	0.733996	0.0	0.001397	0.014987	0.029115	0.000730	0.000730	0.000000	17	0.805109	21.136561	0.524818	0.452555	0.022628	25.202355	7.900000
commons-io	5560	0.033633	0.217446	9.0	145.0	0.016187	0.001799	0.107734	0.680576	0.0	0.000000	0.031862	0.028655	0.000000	0.000000	0.001654	20	0.892473	24.876858	0.493797	0.434243	0.071960	21.744604	16.111111
commons-lang	8614	0.045972	0.263989	10.0	105.5	0.024379	0.001509	0.086951	0.717088	0.0	0.000000	0.018381	0.040930	0.000000	0.000000	0.000440	22	0.933157	24.821353	0.619613	0.359719	0.020668	26.398886	10.550000
commons-logging	1826	0.033406	0.197700	8.0	92.0	0.036692	0.002738	0.171961	0.365279	0.0	0.000000	0.018995	0.027149	0.000000	0.000000	0.000000	13	0.850416	11.760604	0.764543	0.196676	0.038781	19.769989	11.500000
commons-pool	2804	0.085592	1.194722	8.0	81.5	0.016762	0.007133	0.166904	0.529601	0.0	0.000000	0.020874	0.073684	0.000000	0.000000	0.045373	17	0.862388	80.660140	0.640000	0.322985	0.037015	119.472183	10.187500
commons-text	2322	0.020241	0.123600	5.0	336.0	0.071921	0.004307	0.261413	0.444875	0.0	0.000428	0.012485	0.017980	0.010453	0.010453	0.048780	13	0.954704	10.949225	0.801394	0.135889	0.062718	12.360034	67.200000
fastjson-core	2934	0.109748	0.623381	36.0	165.5	0.140082	0.029993	0.103954	0.914110	0.0	0.000000	0.018740	0.101410	0.000000	0.000000	0.004921	23	0.953527	67.188583	0.827775	0.141607	0.030618	62.338105	4.597222
fastjson2-core	4597	0.079835	0.435066	41.0	288.0	0.048727	0.013922	0.219056	0.774636	0.0	0.046233	0.002812	0.069596	0.075500	0.068500	0.001500	20	0.862000	71.829450	0.620000	0.348500	0.031500	43.506635	7.024390
gson	1977	0.054628	0.237734	20.0	120.0	0.070309	0.013151	0.267577	0.669196	0.0	0.109508	0.016023	0.050835	0.751064	0.257447	0.000000	19	0.985106	14.360114	0.651064	0.338298	0.010638	23.773394	6.000000
guava	6972	0.054217	0.292169	31.0	122.5	0.000143	0.000717	0.055221	0.897734	0.0	0.032814	0.028148	0.040945	0.730486	0.092784	0.136475	20	0.974472	30.668046	0.548846	0.349043	0.102111	29.216867	3.951613
h2-database	8024	0.172483	4.238161	37.0	271.5	0.192547	0.002493	0.008724	0.871386	0.0	0.000000	0.000336	0.152342	0.000000	0.000000	0.000706	25	0.899285	471.502985	0.593995	0.386685	0.019320	423.816052	7.337838
hamcrest-core	621	0.077295	0.700483	20.0	80.5	0.069243	0.025765	0.000000	0.611916	0.0	0.053894	0.005599	0.057801	0.018391	0.018391	0.002299	13	0.937931	14.638984	0.434483	0.514943	0.050575	70.048309	4.025000
hibernate-core	4826	0.175300	7.095731	53.0	328.0	0.016162	0.009946	0.013054	0.846042	0.0	0.240281	0.007952	0.127562	0.156787	0.079634	0.021318	27	0.898026	1351.930108	0.666365	0.198341	0.135294	709.573145	6.188679